Skip to content

Conformal Seasonal Pools

Home / Concepts / Conformal Seasonal Pools

Conformal Seasonal Pools

Auto-generated stub. Edit this file to add more details.

A training-free probabilistic forecasting method that generates prediction intervals by combining seasonal empirical observations with historical residuals.

Why It Matters

Represents a new class of training-free, non-parametric conformal forecasting frameworks that serve as a strong performance and calibration benchmark for learned models.

Evidence

We propose Conformal Seasonal Pools (CSP), a training-free probabilistic time-series forecaster that mixes same-season empirical draws with signed residual draws around a seasonal naive forecast.

Metadata & Links